Optimization of Warehouse Supply Chain Operations Using AI-Powered Smart Serving Robots

Abstract

The rapid advancement of artificial intelligence and autonomous robotics has significantly transformed warehouse supply chain operations through intelligent automation and smart logistics systems. This study investigated the optimization of warehouse supply chain operations using AI-powered smart serving robots integrated with machine learning, computer vision, autonomous navigation, and embedded communication technologies. The developed robotic system utilized YOLOv4 object detection, convolutional neural networks, RRT* path planning, ultrasonic sensing, and NVIDIA Jetson TX2 embedded processing to perform autonomous material transportation, obstacle avoidance, and intelligent warehouse navigation. Experimental evaluation demonstrated that the robotic platform achieved reliable real-time object recognition, efficient collision-free navigation, stable communication performance, and adaptive operational coordination within simulated warehouse environments. The implementation of AI-driven navigation and autonomous delivery mechanisms significantly improved transportation efficiency, reduced operational delays, minimized manual workload, and enhanced warehouse logistics productivity. The findings further revealed that intelligent robotic systems can optimize route planning, improve obstacle handling, and support continuous supply chain operations with minimal human intervention. Despite challenges related to computational limitations and dynamic navigation complexity, the study concludes that AI-powered smart serving robots represent an effective solution for intelligent warehouse automation and Industry 4.0 logistics infrastructure. The research highlights the growing importance of autonomous robotic technologies in achieving efficient, reliable, and scalable warehouse supply chain optimization.